检索结果-内蒙古大学图书馆

Deciphering urban traffic impacts on air quality by deep learning and emission inventory

Journal of Environmental sciences 2023年第2期124卷 745-757页

作者： Wenjie Du Lianliang Chen Haoran Wang Ziyang Shan Zhengyang Zhou Wenwei Li Yang Wang School of Software Engineering University of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China Alibaba Inc. Hangzhou 310052China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China CAS Key Laboratory of Urban Pollutant Conversion Department of environmental science and EngineeringUniversity of Science and Technology of ChinaHefei 230026China USTC-CityU Joint Advanced Research Center Suzhou 215123China

Air pollution is a major obstacle to future sustainability,and traffic pollution has become a large drag on the sustainable developments of future ***,combined with the large volume of real-time monitoring data,we propose a deep learning model,iDeepAir,to predict surface-level PM2.5 concentration in Shanghai megacity and link with MEIC emission inventory creatively to decipher urban traffic impacts on air *** model exhibits high-fidelity in reproducing pollutant concentrations and reduces the MAE from 25.355μg/m^(3) to 12.283μg/m^(3) compared with other *** identifies the ranking of major factors,local meteorological conditions have become a nonnegligible ***-wise relevance propagation(LRP)is used here to enhance the interpretability of the model and we visualize and analyze the reasons for the different correlation between traffic density and PM_(2.5) concentration in various regions of ***,As the strict and effective industrial emission reduction measurements implementing in China,the contribution of urban traffic to PM_(2.5) formation calculated by combining MEIC emission inventory and LRP is gradually increasing from 18.03%in 2011 to 24.37% in 2017 in Shanghai,and the impact of traffic emissions would be ever-prominent in 2030 according to our *** also infer that the promotion of vehicular electrification would achieve further alleviation of PM_(2.5) about 8.45% by 2030 *** insights are of great significance to provide the decision-making basis for accurate and high-efficient traffic management and urban pollution control,and eventually benefit people’s lives and high-quality sustainable developments of cities.

关键词： PM_(2.5)concentration forecast Traffic emissions Deep learning Attention mechanism New energy vehicles

来源：评论

学校读者我要写书评

暂无评论

Sparse is Enough in Fine-tuning Pre-trained Large Language Models 41

Sparse is Enough in Fine-tuning Pre-trained Large Language M...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Song, Weixi Li, Zuchao Zhang, Lefei Zhao, Hai Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Luojia Laboratory Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscillations in the loss landscape and the quasi-sparsity in gradient distribution. Based on this, we propose a gradient-based sparse finetuning algorithm, named Sparse Increment Fine-Tuning (SIFT), and validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning. The code is accessible at https://***/song-wx/SIFT. Copyright 2024 by the author(s)

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Multispectral imaging light estimation based on convolutional neural networks

Multispectral imaging light estimation based on convolutiona...

引用

2024 AI Photonics Technology Symposium

作者： Ma, Long Zhao, Fengqi School of science Shenyang Jianzhu University Shenyang110168 China School of Computer Science and Engineering Shenyang Jianzhu University Shenyang110168 China

ISBN: (纸本)9781510681828

In this work, we describe a convolutional neural network (CNN) to accurately predict field lighting. In the network structure, feature learning and regression are integrated into an optimization process to form a more effective model for scene illumination estimation. And we have added an attention mechanism to reinforce learning. This approach is trained with ICVL data sets and tested with Foster HSI data for better performance. The stability of the proposed neural network for local illumination estimation and the improvement of the global illumination estimation performance are verified by experiments on the spatial illumination variation images. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Resource Allocation for ICVs in CFNs via Constrained MARL

Task Offloading and Resource Allocation for ICVs in CFNs via...

引用

2024 IEEE International Symposium on Product Compliance engineering-Asia, ISPCE-AS 2024

作者： Wang, Enshu He, Jinbo Liu, Bingyi Shi, Haiyong Han, Weizhen Wu, Libing School of Cyber Science and Engineering Wuhan University Wuhan China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798331523008

Computing First Network (CFN) aims to enable unified scheduling of computing nodes across the network, positioning it as a promising paradigm for managing the computationally intensive tasks of Intelligent Connected Vehicles (ICVs). Given the highly dynamic vehicle network topology and uneven vehicle density, ICV tasks may fail due to limited computing resource on individual node. Thus, it is crucial for CFN to efficiently schedule I CV tasks and allocate resources to ensure their successful completion. However, existing task scheduling methods often struggle with large action spaces and tend to over-look the correlation between offloading and resource allocation decisions. Additionally, the high computing resource demands of ICV tasks require CFN to allocate resources within constrained range to ensure timely overall task completion. To address these challenges, we propose a Constrained and Action Represented Multi-Agent Reinforcement Learning (CARMARL) framework that generates reliable policies to meet the QoS requirements of I CV tasks while fully utilizing computing resources in CFN. Specifically, CARMARL maintains a Conditional Variational Autoencoder (CVAE) to reduce the action space and enable agents to learn the correlation between offloading and allocation decisions and a Reward Constrained Policy Optimization (RCPO) module to ensure resource allocation remains reasonableness. Extensive experiments demonstrate that CARMARL improves task completion rate by up to 25.2 % compared to all baselines. © 2024 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Container-based data-intensive application scheduling in hybrid cloud-edge collaborative environment

Container-based data-intensive application scheduling in hyb...

引用

作者： Tang, Bing Luo, Jincheng Zhang, Jiaming School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan China Hunan Key Laboratory for Service Computing and Novel Software Technology Hunan University of Science and Technology Hunan Xiangtan China School of Information and Communication Engineering Guangzhou Maritime University Guangdong Guangzhou China School of Information Engineering Wuhan University of Technology Hubei Wuhan China

Container virtualization technology represented by Docker has been widely used in the industry due to its advantages of lightweight, fast deployment, and easy portability. It can bring convenience to system deployment, operation, and maintenance. This article considers the implementation of AI-based IoT applications based on Docker and container technology in a cloud-edge collaborative environment. Three typical data-intensive applications, preprocessing, training, and inference in machine learning, are deployed using Docker containers. For these three types of tasks, this article proposes a container-based data-intensive application scheduling framework. Using an attribute-based data-driven method, a new scheduling approach considering multiple weighting factors is proposed, which is called DICS-OPT. The cloud nodes and edge nodes are scored and sorted uniformly. The container is scheduled to the node with the highest score, and then the task data is transmitted to the node to execute the task. NSGA-III-based genetic algorithm has been proposed to search for the optimal weighting factors. This article introduces the implementation of the prototype system and builds a cloud-edge collaborative testbed consisting of Raspberry Pis and PCs. The performance evaluation results indicates that the proposed scheduling approach outperforms existing approaches. Compared with existing approaches, DICS-OPT improves the average edge resource utilization by 10.05% to 69.04%, and saves the cloud resource cost by 16.02% to 36.68%. © 2023 John Wiley & Sons Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A GMM-CGABC Based Energy Replenishment Scheme for On-Demand Wireless Rechargeable Sensor Networks 1

A GMM-CGABC Based Energy Replenishment Scheme for On-Demand ...

引用

1st International Symposium on Parallel Computing and Distributed Systems, PCDS 2024

作者： Mouli, S.Sudhamsu Veeraiah, T. Mahesh, K. Singh, M.P. Ecole Centrale School of Engineering Mahindra University Department of Computer Science and Engineering Hyderabad India National Institute of Technology Department of Computer Science and Engineering Patna India

ISBN: (纸本)9798350349658

Wireless Sensor Networks (WSNs) are constrained by the limited energy capacity of Sensor Nodes (SNs), which hinders their perpetual operation. The advent of Wireless Energy Transfer (WET) technology has emerged as a promising solution to this challenge, enabling the creation of Wireless Rechargeable Sensor Networks (WRSNs). Recent research has shown growing interest in integrating Wireless Mobile Chargers (WMCs) into WRSNs to replenish the energy reserves of critical SNs through WET. A key aspect of WET involves using one or more WMCs to recharge SNs, with optimizing the charging schedule (i.e., the sequence in which SNs are charged) crucial in on-demand WRSNs. In addition, spatiotemporal constraints imposed by the requesting SNs must be considered when devising the WMC's charging schedule. To address these challenges, this work proposes the integration of a Gaussian Mixture Model with a Chaotic Gaussian Artificial Bee Colony (GMM-CGABC) to develop an efficient recharge schedule that revitalizes SNs. This model is designed to optimize SN deployment, maximize network coverage, minimize energy consumption, and extend network longevity. The proposed method determines the optimal charging path for WMCs within each cluster to minimize Average Charging Latency (ACL) while incorporating a novel strategy for fitness function evaluation. Extensive simulations demonstrate that the proposed system outperforms state-of-the-art algorithms, including First Come, First Served (FCFS), Nearest Job Next with Preemption (NJNP), and the Gravitational Search Algorithm (GSA), in terms of charging latency. © 2024 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

DualDoctor: A Mutual Learning Method with Dynamic Knowledge Transfer and Class-Level Alignment for Classifying Medical Images

DualDoctor: A Mutual Learning Method with Dynamic Knowledge ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Long, Ting Li, Lele Yang, Feng Wang, Yuan Liu, Juan Wuhan University Institute of Artificial Intelligence School of Computer Science Wuhan China Wuhan University School of Cyber Science and Engineering Wuhan China

ISBN: (纸本)9798350386226

Mutual learning that can be seen as a derivative method of knowledge distillation takes advantages of the collective capabilities of multiple neural networks to promote the precision and stability of classification outcomes, and achieved great success in the field of computer vision. Recently, mutual learning has been exploited in the task of medical image classification. However, medical images belonging to different classes may be very similar, which may affect the classification performance of the mutual learning based methods. In this paper, we propose a novel mutual learning model, named DualDoctor, especially for the classification of medical images. DualDoctor is built by embedding the channel and spatial feature-based dynamic knowledge transfer module and the logit-based class alignment module into the vanilla mutual learning framework. The dynamic knowledge transfer module makes two sub-models sharing the critical information at the feature level, while the logit-based class alignment module enforces two sub-models to absorb the class correlation knowledge from each other at the logit level. Therefore, DualDoctor can adapt well to the characteristics of medical images so as to make more accurate classifications. The evaluation results on two public datasets, BUSI and ISIC2018, indicate that the proposed DualDoctor model performs better than the comparison methods in medical image classification tasks. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Wave refrigeration control via deep reinforcement learning 4

Wave refrigeration control via deep reinforcement learning

引用

2024 4th International Conference on Artificial Intelligence and Industrial Technology Applications, AIITA 2024

作者： Cui, Xuesong Hu, Xiaopeng Wang, Fan Li, Qi School of Computer Science and Technology Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China

Wave refrigerating technology is a new type of refrigerating technology that performs more efficiently and is more environmentally friendly. Nowadays, the commonly used control method is the PID control method. However, although the above control methods are simple in structure, they have the problems of difficult parameter tuning, large overshoot, and unstable and inaccurate output response. Therefore, to improve the above problems, we propose a framework of deep reinforcement learning-based wave refrigerating control system. An improved SAC algorithm is used to learn the control system. The evaluation method is established according to the working condition requirements as well as the safety requirements in the operation process. Experiments show that this method can effectively improve the control efficiency as well as the control quality, which can make the control system operate stably. © Published under licence by IOP Publishing Ltd.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

GEOMETRY-AWARE PROJECTIVE MAPPING FOR UNBOUNDED NEURAL RADIANCE FIELDS 12

GEOMETRY-AWARE PROJECTIVE MAPPING FOR UNBOUNDED NEURAL RADIA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Lee, Junoh Jung, Hyunjun Park, Jin-Hwi Bae, Inhwan Jeon, Hae-Gon School of Electrical Engineering and Computer Science Gwangju Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju Korea Republic of

Estimating neural radiance fields (NeRFs) is able to generate novel views of a scene from known imagery. Recent approaches have afforded dramatic progress on small bounded regions of the scene. For an unbounded scene where cameras point in any direction and contents exist at any distance, certain mapping functions are used to represent it within a bounded space, yet they either work in object-centric scenes or focus on objects close to the camera. The goal of this paper is to understand how to design a proper mapping function that considers per-scene optimization, which remains unexplored. We first present a geometric understanding of existing mapping functions that express the relation between the bounded and unbounded scenes. Here, we exploit a stereographic projection method to explain failures of the mapping functions, where input ray samples are too sparse to account for scene geometry in unbounded regions. To overcome the failures, we propose a novel mapping function based on a p-norm distance, allowing to adaptively sample the rays by adjusting the p-value according to scene geometry, even in unbounded regions. To take the advantage of our mapping function, we also introduce a new ray parameterization to properly allocate ray samples in the geometry of unbounded regions. Through the incorporation of both the novel mapping function and the ray parameterization within existing NeRF frameworks, our method achieves state-ofthe-art novel view synthesis results on a variety of challenging datasets. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Investigating the Impact of Bug Dependencies on Bug-Fixing Time Prediction 17

Investigating the Impact of Bug Dependencies on Bug-Fixing T...

引用

17th ACM/IEEE International Symposium on Empirical software engineering and Measurement, ESEM 2023

作者： Li, Chenglin Zhao, Yangyang Yang, Yibiao Zhou, Yuming Nie, Liming Ding, Zuohua School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou China Nanjing University State Key Lab for Novel Software Technology Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781665452236

Background: Bug dependencies refer to the link relationships between bugs and related issues, which are commonly observed in software evolution. It has been found that bugs with bug dependencies often take longer time to be resolved than other bugs without any dependencies. Despite the potential impact of bug dependencies on bug-fixing time, previous studies use traditional metrics without considering bug dependencies to build bug-fixing time prediction models. As a result, there is currently little empirical evidence to support the use of bug dependencies in improving prediction accuracy. Aims: We aim to conduct a comprehensive empirical study to investigate the value of considering bug dependencies for bug-fixing time prediction. Method: We define a set of bug dependency metrics based on bug dependencies. We first investigate the correlation between bug dependency metrics and bug-fixing time to investigate whether bugs with more complex dependencies are more time-consuming to be fixed. Next, we employ principal component analysis to study whether bug dependency metrics capture additional dimensions of a bug compared to traditional metrics. Finally, we build multivariate prediction models to explore whether considering bug dependencies can improve the effectiveness of bug-fixing time prediction. Results: The experimental results suggest that: (1) bugs with more complex dependencies require more time to be fixed;(2) bug dependency metrics are complementary to traditional metrics;(3) considering bug dependencies can improve the effectiveness of bug-fixing time prediction. Conclusions: These findings highlight the importance of considering bug dependencies in bug-fixing time prediction, and provide valuable insights into the potential impact of bug dependencies on software development processes. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：